Skip to main content
This guide shows you how to connect a Claude-powered agent to Caylex using the Claude Agent SDK.

​
Prerequisites

​
Installation

pip install claude-agent-sdk

​
Full example

main.py
import asyncio
import os

from claude_agent_sdk import query, ClaudeAgentOptions, MCPServerStreamableHttp


async def main() -> None:
    api_key = os.environ["CAYLEX_API_KEY"]
    user_email = os.environ["CAYLEX_USER_EMAIL"]

    # Connect to Caylex MCP
    caylex_server = MCPServerStreamableHttp(
        name="Caylex",
        url="https://proxy.caylex.ai/mcp",
        headers={
            "x-api-key": api_key,
            "x-user-email": user_email,
        },
    )

    # Run the agent with Caylex tools
    async for message in query(
        prompt="Check my Linear issues, find any blockers, and post updates to the relevant Slack channels.",
        options=ClaudeAgentOptions(
            model="claude-opus-4-5",
            mcp_servers=[caylex_server],
        ),
    ):
        if hasattr(message, "result"):
            print(message.result)


asyncio.run(main())

​
Step-by-step

1

Set environment variables

export CAYLEX_API_KEY="ck_abc123.your-secret-key"
export CAYLEX_USER_EMAIL="user@example.com"
export ANTHROPIC_API_KEY="your-anthropic-key"
2

Create the MCP server connection

Use MCPServerStreamableHttp with the Caylex endpoint and authentication headers.
caylex_server = MCPServerStreamableHttp(
    name="Caylex",
    url="https://proxy.caylex.ai/mcp",
    headers={
        "x-api-key": api_key,
        "x-user-email": user_email,
    },
)
3

Run the agent with streaming

Use the query function with ClaudeAgentOptions to run the agent. The response streams as the agent works through its reasoning and tool calls.
async for message in query(
    prompt="Your query here.",
    options=ClaudeAgentOptions(
        model="claude-opus-4-5",
        mcp_servers=[caylex_server],
    ),
):
    if hasattr(message, "result"):
        print(message.result)

​
Further reading